[user8341116]

Bahahaahhahahahaha. O-our chatbot got taken advantage of! We were completely blind that this could possibly happen! But they're the worst of humanity, the people that found an exploit not the engineers who are incapable of implementing even simple safeguards!!

[chaz72]

Sounds easy! So what does your plan to implement "simple safeguards" for a chatbot on Twitter look like?

[stared]

For starter: penalizing generated phrases with obscene words, "hate", "kill", "Hilter" and a few other.

[Nadya]

"I really hate Hitler. If he were alive today, I'd kill him."

Want to give a reason that should be a heavily penalized phrase?

[jackvalentine]

It's safer to just avoid Hitler altogether.